© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23476
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    323
    +0.14
    0.8%
    483
    +0.13
    0.7%
    264
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.14
    0.05
    403
    +0.13
    0.04
    274
    +0.12
    0.05
    Negative Logits
    ĻĤ
    -3.82
    ¿½
    -3.82
    ĸ´
    -3.57
    IJ
    -3.54
               ↵
    -3.27
    -3.27
    ↵  âĢĥ
    -3.27
    ↵
    -3.27
    ↵↵
    -3.27
    <|outofrange|>
    -3.27
    POSITIVE LOGITS
    cit
    1.82
    tp
    1.62
    local
    1.62
    tig
    1.61
    connections
    1.57
    place
    1.56
    eca
    1.52
    control
    1.52
    calc
    1.52
    unc
    1.50
    Activations Density 0.303%

    No Known Activations